Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/coltonbearden/carrelWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/coltonbearden/carrel/diff)<a href="https://agentmods.dev/commands/coltonbearden/carrel/diff"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/diff/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/coltonbearden/carrel/diff"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/diff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.00685 |
| Opus 5.5 | $0.00012 | $0.00274 |
| Sonnet 5.5 | $0.00006 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
diff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Compare the two files the user asked about: $ARGUMENTS
Run the carrel CLI via Bash. Map the user's request onto the real flags in the --help block below (regenerated from the CLI by scripts/sync_plugins.py; if the installed carrel diff --help differs, trust the installed version — never invent flags):
Usage: carrel diff [OPTIONS] A B
Compare two files A and B.
Modes: text (unified diff), struct (json: dotted-path added/removed/changed; csv: per-row/column
cell changes; xml: element-path changes), pdf (extracted text diff + page counts), image (Pillow
pixel diff: dimensions, changed-pixel percentage, mean channel delta; sizes are padded to a common
canvas and the mismatch reported). auto picks by type pair and falls back to a text diff when both
files are text-like.
Exit status:
0 files are identical
1 files differ
2 bad usage
3 missing optional dependency (pdf mode needs pdftotext)
4 missing/unsupported input, or no mode fits the type pair
Options:
--json Machine-readable JSON output.
--mode [auto|text|struct|image|pdf]
Comparison strategy; auto picks by type pair. [default: auto]
--out FILE Image mode: write a per-pixel delta heatmap PNG here.
--help Show this message and exit.
--mode auto(default) picks by type pair; only override when the user asks for a specific comparison:text: unified diff.struct: json (dotted-path added/removed/changed), csv (per-row/column cell changes), xml (element-path changes).pdf: extracted-text diff plus page counts.image: Pillow pixel diff — dimensions, changed-pixel percentage, mean channel delta.
--out FILE(image mode only): writes a per-pixel delta heatmap PNG — offer this when comparing images.
Interpret the exit code first: 0 = identical, 1 = files differ (that's data, not an error), 2 = bad usage, 3 = missing optional dependency (pdf mode needs pdftotext — relay the install hint), 4 = missing/unsupported input or no mode fits the type pair. Then summarize the differences for the user: what changed, where, and how much — not a raw dump.
Requires the carrel CLI on PATH. If carrel is not found, tell the user to install it with uv tool install carrel (see the repo's INSTALL notes), or run it as uv run carrel ... from the carrel repo root.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +25 lines 79289e59f5bb
- 1mo ago Changed a7ea11141234
- 1mo ago First seen · 25 lines · 29 tokens per session scan A d16cc8a29953
diff is a command published in the GitHub repository coltonbearden/carrel (2 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 685 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
add-agent
Add a new sub-agent to the current plugin for specialized tasks.
add-command
Add a new slash command to the current plugin.
add-skill
Add a new Skill to the current plugin with proper structure.
init
Scaffold a new Claude Code plugin with standard structure and starter files.
hello
Greet the user with a friendly, personalized message.
run-quality-gates
Run code quality checks (lint, format, type check, tests).